README.md · QuantStack/Wan2.1_T2V_14B_FusionX_VACE-GGUF at d0f8ce401e78742a25635275c32d21129f1894c5

metadata

base_model:
  - QuantStack/Wan2.1-14B-T2V-FusionX-VACE
base_model_relation: quantized
library_name: gguf
quantized_by: lym00
tags:
  - text-to-video
  - image-to-video
  - video-to-video
  - quantized
language:
  - en
license: apache-2.0

This is a GGUF conversion of QuantStack/Wan2.1-14B-T2V-FusionX-VACE.

All quantized versions were created from the base FP16 model using the conversion scripts provided by city96, available at the ComfyUI-GGUF GitHub repository.

Usage

The model files can be used in ComfyUI with the ComfyUI-GGUF custom node. Place the required model(s) in the following folders:

Type	Name	Location	Download
Main Model	Wan2.1-14B-T2V-FusionX-VACE-GGUF	`ComfyUI/models/unet`	GGUF (this repo)
Text Encoder	umt5-xxl-encoder	`ComfyUI/models/text_encoders`	Safetensors / GGUF
VAE	Wan2_1_VAE_bf16	`ComfyUI/models/vae`	Safetensors

ComfyUI example workflow

Notes

All original licenses and restrictions from the base models still apply.

Reference

For more information about the source model, refer to QuantStack/Wan2.1-14B-T2V-FusionX-VACE, where the model creation process is explained.
For an overview of quantization types, please see the GGUF quantization types.